mermaid-to-excalidraw-mcp
MCP server that converts Mermaid diagrams to styled Excalidraw files, saving them directly to disk without token overhead.
README
mermaid-to-excalidraw-mcp
MCP server that converts Mermaid diagrams to styled Excalidraw files.
Generated with Claude Code. AI slop included, but it helps me every day :)
The Problem
When asking Claude to create diagrams, you have two bad options:
-
Generate Excalidraw JSON directly - Works, but costs ~500 tokens per shape. A simple 5-node diagram = 2500+ tokens of JSON in Claude's response.
-
Use existing mermaid-to-excalidraw - Token-efficient input, but strips all colors and requires a browser.
The Solution
This MCP server lets Claude write compact Mermaid (30 tokens) and outputs styled .excalidraw.md files directly to disk - no tokens wasted on JSON output.
You: "Create an architecture diagram: React -> API -> PostgreSQL + Redis"
Claude writes: ~50 tokens of Mermaid
Output: Styled diagram saved to file

Setup
git clone https://github.com/yannick-cw/mermaid-to-excalidraw-mcp
cd mermaid-to-excalidraw-mcp && npm install && npm run build
Add to ~/.claude.json:
{
"mcpServers": {
"mermaid-excali": {
"command": "node",
"args": ["/absolute/path/to/mermaid-to-excalidraw-mcp/dist/index.js"]
}
}
}
Usage
Just ask Claude to create a diagram and specify where to save it:
"Create an ER diagram for a blog system with users, posts, and comments. Save to ~/diagrams/blog.excalidraw.md"
The output file opens directly in Obsidian (with Excalidraw plugin) or can be imported to excalidraw.com.
Features
Diagram types: Flowcharts, sequence diagrams, ER diagrams
Semantic colors - Add a directive to color nodes by type:
%%{excali: styles: {FE: ui, API: api, DB: db, Cache: cache}}%%
flowchart TD
FE[React App] --> API[Node Service]
API --> DB[(PostgreSQL)]
API --> Cache[Redis]
Available styles: ui api db cache queue gateway external agent storage user orchestrator problem solution highlight
Connected arrows - shapes stay linked when you move them
Embedded source - original Mermaid preserved in the file for portability
More Examples


Inspired by
- mermaid-to-excalidraw - the original, browser-based
- obsidian-excalidraw-plugin - what makes
.excalidraw.mdwork
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.